KR20230082885A - Performance evaluation methods and perfromace evaluation system for autonomous driving robot - Google Patents

Abstract

The present invention relates to a method and system for evaluating the performance of an autonomous driving robot, and an exemplary embodiment of the present invention relates to a method for evaluating the performance of an autonomous driving robot. After the selection setting step and the setting step, the route planning evaluation step of evaluating the time required for the robot to plan a route from the starting point to the target point, and after the route planning evaluation step, the self-driving performance of the robot is evaluated. It provides a performance evaluation method of an autonomous driving robot including an autonomous driving performance evaluation step.

Description

Performance evaluation method and performance evaluation system of autonomous driving robot {PERFORMANCE EVALUATION METHODS AND PERFROMACE EVALUATION SYSTEM FOR AUTONOMOUS DRIVING ROBOT}

The present invention relates to a method and system for evaluating the performance of an autonomous robot.

In general, robot driving refers to a technology system that creates and controls a route from a current location to a destination based on environmental and location information. It is applied and implemented in various products, including robots.

In other words, robot driving implements the mobility function of a robot, and an autonomous robot is defined as a robot that searches its surroundings and detects obstacles on its own, selects the optimal path using means of transportation such as wheels or legs, and finds its destination. It can be.

The general structure of robot autonomous driving technology is localization, mapping, driving control (guidance/control), precision of element information (level of detail), spatial recognition-based local path creation and autonomous control, etc. can include

Robot driving function is largely divided into map-based navigation, map building-based navigation, and mapless navigation according to the method of using spatial information. possible.

In the case of map-based navigation, it is a method of driving using map information previously created by the user, including CAD data. Based on the sensing information about the environment, it is a method of creating a map necessary for driving on its own. Accordingly, development of SLAM (Simultaneous Localization And Map-Building) technology is continuously being researched.

Mapless navigation is a method of driving by recognizing landmarks or objects in the driving environment.

In the case of the self-driving robot described above, it can be manufactured with various specifications, and since there is a difference in autonomous driving performance according to each specification, the development of a method and system capable of quantitatively evaluating the performance of the autonomous driving robot is required.

Accordingly, an object of the present invention is to solve the above problems.

One of the various tasks of the present invention is to provide a method and system capable of quantitatively evaluating the performance of an autonomous robot manufactured with various specifications.

One of the various tasks of the present invention is to provide an evaluation section that implements various environments for performance evaluation of an autonomous robot.

One of the various tasks of the present invention is to provide a method and system capable of evaluating the ability to generate a map in the case of a robot to which SLAM (Simultaneous Localization And Map-Building) technology is applied.

One of the various tasks of the present invention is to provide a method and system capable of evaluating position accuracy and repetition accuracy for autonomous driving performance of a robot.

One of the various tasks of the present invention is to provide a method and system capable of evaluating the ability of a robot to select or create an optimal path and establish a path plan when a starting point and a target point are provided to the robot.

Various embodiments for solving the problems of the present invention, in the performance evaluation method of an autonomous driving robot, a setting step of selecting a starting point and a target point for self-driving performance evaluation of the robot, and after the setting step, the robot moves to the starting point Self-driving robot performance evaluation including a route planning evaluation step of evaluating the time required to plan a path from the route to the target point and an autonomous driving performance evaluation step of evaluating the autonomous driving performance of the robot after the route planning evaluation step. provides a way

The setting step may include determining whether Simultaneous Localization And Map-Building (SLAM) technology is applied to the robot.

When the SLAM technology is applied to the robot, the map generation ability of the robot can be evaluated.

The evaluation of the map generation ability may include evaluating a map generation speed based on a time required for the robot to generate a map.

The step of evaluating the map generation ability may further include the step of evaluating the generation accuracy of the map based on the matching rate between the generated map and the map data of the evaluation environment stored in the server after evaluating the generation speed of the map. can

The route planning evaluation step may include determining whether the route planning of the robot has been completed, and when the route planning of the robot has been completed, the time required for the robot to complete the route planning exceeds a predetermined time. It may include the step of determining whether or not.

The self-driving performance evaluation step may include evaluating position accuracy of the robot based on a difference between a position of the robot and a position of the target point when the robot reaches the target point.

The position precision evaluation step may include determining whether the robot has reached the target point, measuring a position error between the target point and the robot when the robot has reached the target point, and determining whether the measured position error is A step of determining whether the set value is exceeded may be included.

The self-driving performance evaluation step may further include evaluating repetition accuracy of the robot based on a position difference between a position of the robot and a position of the target point when the robot repeatedly travels between the starting point and the target point. .

The repetition precision evaluation step may include accumulative summing of the position errors measured for each number of travels when the number of travels of the robot satisfies a predetermined number of times, and whether the accumulated and summed position error value exceeds a predetermined value. It may include the step of determining.

In an exemplary embodiment of the present invention, in a system for performance evaluation of an autonomous driving robot, a map generation and storage unit for generating environment map information for robot performance evaluation and storing at least one map data, and the performance of the robot A position setting unit that sets a starting point and a target point for evaluation, and a path planning evaluation unit that evaluates the time required for the robot to plan a path from the starting point to the target point, communicates with the robot and receives data from the robot, or Performance evaluation of an autonomous robot including a communication unit that transmits commands, a position measuring unit that measures the position of the robot, and an autonomous driving performance evaluation unit that evaluates the autonomous driving performance of the robot based on the position measured through the position measuring unit. provide the system.

The position setting unit may include an obstacle generating unit for placing at least one obstacle on a driving path of the robot determined by the starting point and the target point.

When the SLAM technology is applied to the robot, the robot may further include a SLAM technology evaluation unit that evaluates a map generation speed based on a time required for the robot to generate a map.

The SLAM technology evaluation unit may evaluate a matching rate between the generated map and map data of an evaluation environment stored in the map generation and storage unit after evaluating the map generation speed.

The self-driving performance evaluation unit may evaluate position accuracy and repetition accuracy of the robot based on a position difference between the robot and the target point.

Each feature of the above-described embodiments may be implemented in combination in other embodiments unless inconsistent with or exclusive of the other embodiments.

According to various embodiments of the present invention, it is possible to quantitatively evaluate the performance of self-driving robots manufactured with various specifications, and it is possible to implement various environments for performance evaluation of self-driving robots.

In addition, in the case of a robot to which SLAM (Simultaneous Localization And Map-Building) technology is applied, the ability to create a map can be evaluated.

In addition, it is possible to evaluate the location accuracy and repetition accuracy of the robot's autonomous driving performance.

In addition, if a starting point and a goal point are provided to the robot, the ability of the robot to select or create an optimal route and establish a route plan can be evaluated.

Effects of the present invention are not limited to those described above, and other effects not mentioned will be clearly recognized by those skilled in the art from the description below.

1 is a diagram showing a performance evaluation system of an autonomous driving robot according to an embodiment of the present invention.
FIG. 2 is a diagram showing a performance evaluation system of the self-driving robot of FIG. 1, an evaluation section, a robot, and a cloud server.
3 is a diagram schematically illustrating a performance evaluation method of an autonomous driving robot according to an embodiment of the present invention.
4 is a diagram schematically illustrating a method for evaluating the performance of an autonomous robot including a method for evaluating the ability of the robot to generate a map according to an embodiment of the present invention.
FIG. 5 is a diagram showing a performance evaluation method of the self-driving robot of FIG. 4 in detail.
FIG. 6 is a diagram illustrating a method for evaluating map generation ability in FIG. 5 .
FIG. 7 is a diagram illustrating a method for evaluating position accuracy of the robot in FIG. 5 .
FIG. 8 is a diagram illustrating a method for evaluating repetition accuracy of the robot in FIG. 5 .

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The detailed descriptions that follow are provided to provide a comprehensive understanding of the methods, devices and/or systems described herein. However, this is only an example and the present invention is not limited thereto.

In describing the embodiments of the present invention, if it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or operator. Therefore, the definition should be made based on the contents throughout this specification. Terminology used in the detailed description is only for describing the embodiments of the present invention and should in no way be limiting. Unless expressly used otherwise, singular forms of expression include plural forms. In this description, expressions such as "comprising" or "comprising" are intended to indicate any characteristic, number, step, operation, element, portion or combination thereof, one or more other than those described. It should not be construed to exclude the existence or possibility of any other feature, number, step, operation, element, part or combination thereof.

Also, terms such as first, second, A, B, (a), and (b) may be used in describing the components of the embodiment of the present invention. These terms are only used to distinguish the component from other components, and the nature, order, or order of the corresponding component is not limited by the term.

1 and 2 are diagrams showing a performance evaluation system of an autonomous driving robot according to an embodiment of the present invention.

It will be described with reference to FIG. 1 below.

The performance evaluation system 100 of an autonomous robot according to an embodiment of the present invention includes a specification setting unit 110, a calculation unit 120, a position measurement unit 130, a path planning evaluation unit 140, and a communication unit 150. , a map creation and storage unit 160, a location setting unit 170, an autonomous driving performance evaluation unit 180, and a Simultaneous Localization And Map-Building (SLAM) technology evaluation unit 190.

The specification setting unit 110 may store specifications of the self-driving robot to be evaluated. Since the performance of self-driving robots depends on differences in various specifications, it is necessary to set criteria such as evaluation environment and evaluation items according to various self-driving robots in order to increase the reliability of evaluation.

For example, when the SLAM technology is applied to the self-driving robot through the specification setting unit 110, the map generation capability of the evaluation environment for the SLAM technology may be evaluated through a performance evaluation method described later.

The calculation unit 120 may plan a path through a starting point and a target point, and perform various calculation tasks in evaluating an autonomous robot that travels along the planned path at least once.

The position measurement unit 130 may plan a path through the starting point and the target point, and measure the position of the robot in evaluating an autonomous robot that travels along the planned path at least once.

When the starting point and the target point are provided to the robot, the route planning evaluation unit 140 may evaluate the optimal route planning ability of the robot from the starting point to the target point.

The communication unit 150 communicates with the robot, the cloud, various sensors installed in the evaluation environment, etc., and may receive data or transmit commands to the robot. The role of the communication unit is not limited thereto, and can transmit/receive data with various external devices, as well as transmit result data of each evaluation item as an example of an evaluation result of an autonomous robot.

The map generation and storage unit 160 may generate a map of the evaluation environment or store a plurality of preset map data. As described above, the evaluation environment may be differently provided according to autonomous driving robots having various specifications.

The location setting unit 170 may include a setting unit 171 for setting a starting point and a target point and an obstacle generating unit 173.

The starting point and target point setting unit 171 may set a point for starting evaluation of the robot and a point to be reached by driving the robot within the evaluation environment of the self-driving robot.

The obstacle generating unit 173 may set at least one or more obstacles disposed on the driving path of the robot determined as the starting point and the target point in the evaluation environment. Obstacles may include uneven ground, pothole terrain, variable obstacles, and the like. In the case of a variable obstacle, it can be formed in a size considering the recognition ability of the robot, and can be formed in various shapes such as a wall, a cylindrical column, and a square column.

The obstacle generation unit 173 may generate various variables between a starting point and a target point through the above-described obstacles. For example, when an obstacle is not placed on the driving path, the robot can travel in the shortest straight line distance from the starting point to the target point, and when the obstacle is placed on the path through the obstacle generator 173, the robot can avoid the obstacle. It can travel along the path, and obstacles can be placed on the path of the robot so that the robot can travel in a specific shape.

The autonomous driving performance evaluation unit 180 may include a location precision evaluation unit 181 and a repetition precision evaluation unit 183 . The positional accuracy and repeatability of the robot can be evaluated based on the difference between the position of the robot and the target point (positional error between the target point and the robot) when the robot measured or calculated by the above configuration reaches the target point.

The SLAM technology evaluation unit 190 may evaluate SLAM performance when the SLAM technology is applied to the robot. The evaluation criterion of SLAM performance can evaluate the time required for map generation (map building speed) and the accuracy of map generation (map building accuracy).

FIG. 2 is a diagram showing a performance evaluation system of the self-driving robot of FIG. 1, an evaluation section, a robot, and a cloud server.

It will be described with reference to FIG. 2 below.

The performance evaluation system 100 of the self-driving robot according to the present embodiment may perform a communication function through the evaluation section 200, the robot 300, the cloud server 400, and the communication unit 150.

More specifically, according to the embodiment, the communication unit 150 includes a lidar sensor, a radar sensor, etc. disposed in the evaluation section 200 in which the robot 300 travels to measure position or measure movement. It is possible to receive information acquired by various sensors for In addition, result data when evaluation of the self-driving robot is completed or evaluation result data in each section for performance evaluation of the self-driving robot may be transmitted to the cloud server 400 .

The communication unit 150 is connected to the evaluation section 200, the robot 300, and the cloud server 400 through wireless communication, and may support a wireless network such as Wi-Fi on its own, in addition to various communication methods for wireless communication. may include a radio frequency (RF) chip or circuit supporting

The robot 300 may refer to various types of robots including components for autonomous driving.

More specifically, the robot may include a location recognition unit to recognize a driving space and estimate its own location through the location recognition sensor. The location recognizer may use at least one of Global Positioning System (GPS) coordinates, a sensing value of an Inertial Measurement Unit (IMU), and SLAM technology.

In addition, the robot 300 may include a mapping unit to process mapping with the current location or create a map in conjunction with the location recognition unit. The mapping unit may create a map of the driving space or manage a previously created map while the robot 300 performs autonomous driving.

More specifically, the mapping unit creates an accurate map of the driving space without external help through various sensors attached to the mobile robot while moving around the unknown driving space, or SLAM (Simultaneous Localization) to match the driving space with a previously stored map. and mapping) or concurrent mapping and localization (CML). In addition, the mapping unit 164 may use a technique such as structure from motion (SFM) for converting 2D data of a camera into 3D information to generate a 3D map.

In addition, the robot 300 may include a path generator that generates an optimal path for traveling from a starting point to a destination.

More specifically, the route generator may plan a route for autonomous driving of the robot 300 . For example, the path generation unit may use a Rapidly-exploring Random Tree (RRT), an A-star algorithm, a D-star algorithm, or a Dijkstra algorithm for finding a path.

Through the path creation unit, the robot 300 may plan a new path when encountering obstacles while driving in the evaluation environment along the corresponding path. Alternatively, an optimal path may be created based on location information of pre-set obstacles.

3 is a diagram schematically illustrating a performance evaluation method of an autonomous driving robot according to an embodiment of the present invention.

Hereinafter, it will be described with reference to FIG. 3 .

The performance evaluation method of the self-driving robot according to the present embodiment may include a setting step (S11), a route planning establishment evaluation step (S15), a location precision evaluation step (S173), and a repetition precision evaluation step (S175).

In the setting step (S11), map data of an evaluation environment for performance evaluation of the self-driving robot based on the specifications of the robot to be evaluated, and start and target points for evaluation may be transmitted to the robot.

In the route planning establishment evaluation step (S15), the ability of the robot to establish an optimal route plan to reach a goal point from a starting point can be evaluated, and the evaluation of route planning is performed according to the specifications of the robot to be evaluated. It can be evaluated through the amount of time it takes.

Position precision evaluation (S173) and repetition accuracy evaluation (S175) can be evaluated based on the position error of the target point and the robot when the robot reaches the target point, and more details will be described with reference to the drawings below.

4 is a diagram schematically showing a method for evaluating the performance of an autonomous robot including a method for evaluating the ability of the robot to generate a map according to an embodiment of the present invention.

Referring to FIG. 4 , as described above, the performance evaluation target robot of the present embodiment may correspond to both a robot having a function such as SLAM capable of generating a map by itself and a robot incapable of generating a map. Therefore, in this embodiment, it is possible to obtain the specifications of the robot through the setting step (S11) and determine whether or not to provide map data of the evaluation environment based on the specifications of the robot (S113).

More specifically, in the case of a robot to which the SLAM technology is applied, there is no need to provide map data of the evaluation environment, and in this case, the map generation performance of the robot can be evaluated (S13). And in the case of a robot to which SLAM technology is not applied, after providing map data, it is determined whether the robot has planned a route to reach from the starting point to the target point (S151), and then a driving command is transmitted to the robot (S171) to determine the location accuracy Evaluation (S173) and repetition precision evaluation (S175) may be performed.

5 is a diagram showing a performance evaluation method of the self-driving robot of FIG. 4 in detail, FIG. 6 is a diagram showing a map generating capability evaluation method in FIG. 5, and FIG. FIG. 8 is a diagram showing a method for evaluating repetition accuracy of the robot in FIG. 5 .

It will be described with reference to FIGS. 5 to 8 below.

Since self-driving robots having various specifications can be adopted as the target robot for the performance evaluation of the self-driving robot according to the present embodiment, a step of acquiring the specifications of the test-target robot and defining the test-target robot (S111) may be included.

Based on the information acquired in the step of defining the robot to be tested (S111), it can be determined whether or not the SLAM technology is applied to the robot (S113). When the SLAM technology is applied, the robot can create a map within the space of the evaluation environment by itself, so there is no need to transmit the map data of the evaluation environment to the robot. In addition, in the case of a robot where SLAM technology is not applied, map data of an evaluation environment can be transmitted to the robot.

Therefore, it is determined whether the SLAM technology is applied to the robot (S113), and if the SLAM technology is not applied to the robot, the map data of the evaluation environment can be transmitted to the robot (S115). In addition, if the SLAM technology is applied to the robot, the robot's map generation ability can be evaluated.

In more detail about the map generation capability evaluation, the performance evaluation system 100 of the self-driving robot transmits a map generation command to the robot through the communication unit 150 (S131) and determines whether map generation is completed (S132). ), and when the map generation is completed, the map generation ability of the robot can be evaluated (S133).

Referring to FIG. 6, the map generation ability evaluation (S133) is the step of evaluating the map-building speed based on the time required for the robot to create a map, and the generated map data and stored in the server. A step of evaluating map generation accuracy of the robot based on a matching rate with map data of an evaluation environment may be included.

The server in which the above-described map data is stored may mean the performance evaluation system 100 or the cloud server 400 of the self-driving robot.

Evaluating the map generation speed may include determining whether the time required for the robot to generate the map exceeds a preset time (S1331). If the time taken by the robot to generate the map exceeds the predetermined time, the robot does not reach the evaluation standard, so the resulting data may be transmitted to the cloud server (S1332) and reflected in the evaluation.

However, it goes without saying that not only when the robot does not reach the criteria for evaluation, but also when the robot creates a map, the time spent may be transmitted to the cloud server and evaluated through this. This can be equally applied to all cases described later.

After the step of evaluating the map generation speed of the robot described above, matching (S1333) with the generated map and previously stored map data may be performed. In addition, it is determined whether the matching rate between the created map and the previously stored map exceeds a preset value (S1334), and if the matching rate exceeds the preset value, the resulting data is transmitted to the cloud server (S1335) and the starting point And the target point can be set (S117).

On the other hand, in the step of determining whether map generation has been completed (S132), if the map generation is not completed, it is determined whether or not it corresponds to the failure condition (S134), and if it corresponds to the failure condition, the robot generates a map by itself. Map data can be transmitted to the robot (S115) since it corresponds to a case where a problem occurs in the SLAM technology. And if it does not correspond to the failure condition, a map generation command may be transmitted to the robot again (S131).

After the map data is transmitted (S115), a starting point and a target point for self-driving performance evaluation may be set (S117) and transmitted to the robot.

The robot can plan an optimal path based on the acquired starting point and target point. In this embodiment, the path planning ability of the robot can be evaluated based on the time required for path planning.

More specifically, if the path planning is completed after determining whether the path planning of the robot has been completed (S151), it may be determined whether the time required for path planning exceeds a predetermined time (S153). . And, if the route planning is not completed, setting a starting point and a target point (S117) may be performed.

If the time required to establish the route plan exceeds the predetermined time, the resulting data may be transmitted to the cloud server (S155) and a driving command may be transmitted to the robot (S171). In addition, when the time required to establish the route plan is less than a predetermined time, a driving command may be transmitted to the robot (S171).

After transmitting the driving command to the robot (S171), it may be determined whether the robot has reached the target point (S172). When the robot reaches the target point, position accuracy of the robot may be evaluated (S173), and when the robot fails to reach the target point, it may be determined whether or not a failure condition exists (S176).

The failure condition may include a serious hardware failure or software failure to the extent that the robot cannot continue driving for performance evaluation, and performance evaluation may be terminated when the failure condition is met. In addition, if the failure condition does not apply, a driving command may be transmitted to the robot (S171).

Referring to FIG. 7 , position accuracy evaluation (S173) may be evaluated based on a position error between the robot and the target point.

More specifically, when the robot reaches the target point, the position of the robot is measured through the position measurement unit 130 (S1731), and the position from the measured robot position to one position (center) of the target point to the center position of the robot. After measuring the error (S1732), it is possible to evaluate the positional accuracy of the robot by determining whether the measured position error exceeds a preset value (S1733).

When the measured position error exceeds a predetermined value, the resulting data may be transmitted to the cloud server (S1734), and the number of driving times of the robot may be counted (S174). In addition, when the measured position error is less than or equal to a predetermined value, a step of counting the number of driving times of the robot (S174) may be performed.

The step of counting the number of times the robot travels (S174) may mean a step of determining whether or not the number of times the robot travels meets a predetermined number. A more specifically set robot may travel to the set start point and target point multiple times in order to increase the reliability of the performance evaluation of the self-driving robot.

Therefore, if the number of times the robot travels satisfies the predetermined number of times, this corresponds to the case where the robot satisfies all the number of times the robot travels for evaluation, so the repetition accuracy of the robot can be evaluated (S175), and the number of times the robot travels exceeds the predetermined number of times. If not satisfied, a driving command may be transmitted to the robot (S171).

Referring to FIG. 8 , in the step of evaluating the repeatability of the robot (S175), the cumulative position errors measured for each number of driving may be summed (S1741), and the summed result may be evaluated as a standard.

More specifically, through the position measuring unit 130 and the calculating unit 120, the position errors of the robot and the target point measured for each driving count are summed up (S1741), and it is determined whether the summed result value exceeds a preset value. (S1742) Yes.

The step of cumulatively summing the position errors (S1741) is not limited to the present embodiment, and may be based on the average of the measured position errors or the sum or average of values other than the maximum and minimum values to minimize noise. Of course, it can be based on calculation.

When the summed result value exceeds the preset value, the result data may be transmitted to the cloud server (S1743), and the driving result data of the robot may be transmitted to the cloud server (S177). In addition, when the summed result value is less than or equal to the predetermined value, a step of transmitting the driving completion result data of the robot to the cloud server (S177) may be performed.

Although various embodiments of the present invention have been described in detail above, those skilled in the art will understand that various modifications are possible to the above-described embodiments without departing from the scope of the present invention. . Therefore, the scope of the present invention should not be limited to the described embodiments and should not be defined, and should be defined by not only the claims to be described later, but also those equivalent to these claims.

100: Performance evaluation system of autonomous driving robot 300: Robot
200: evaluation section (evaluation environment) 400: cloud server

Claims (15)

In the performance evaluation method of autonomous driving robot,
A setting step of selecting a starting point and a target point to evaluate autonomous driving performance of the robot;
After the setting step, a path planning evaluation step of evaluating a time required for the robot to plan a path from the starting point to the target point; and
An autonomous driving performance evaluation step of evaluating autonomous driving performance of the robot after the path planning evaluation step; According to claim 1,
The setting step may include determining whether SLAM (Simultaneous Localization And Map-Building) technology is applied to the robot. According to claim 2,
A performance evaluation method of an autonomous robot, characterized in that for evaluating the map generation ability of the robot when the SLAM technology is applied to the robot. According to claim 3,
The method for evaluating the performance of an autonomous driving robot, characterized in that the step of evaluating the map generation capability comprises: evaluating a map generation speed based on the time required for the robot to generate a map. According to claim 4,
The step of evaluating the map generation ability further includes: evaluating the generation speed of the map and then evaluating the map generation accuracy based on the matching rate between the generated map and the map data of the evaluation environment stored in the server. Performance evaluation method of an autonomous driving robot, characterized in that. According to claim 1,
The route planning evaluation step may include determining whether the route planning of the robot has been completed; and
When the route planning of the robot is completed, determining whether the time taken for the robot to complete the route planning exceeds a preset time; a performance evaluation method for an autonomous robot comprising: . According to claim 1,
The self-driving performance evaluation step may include evaluating positional accuracy of the robot based on a difference between a position of the robot and a position of the target point when the robot reaches the target point. performance evaluation method. According to claim 7,
The position accuracy evaluation step may include determining whether the robot has reached the target point;
measuring a positional error between the target point and the robot when the robot reaches the target point; and
A method for evaluating the performance of an autonomous robot comprising: determining whether the measured position error exceeds a preset value. According to claim 7,
The self-driving performance evaluation step further includes: evaluating repetition accuracy of the robot based on a position difference between the position of the robot and the target point when the robot repeatedly travels between the starting point and the target point. A method for evaluating the performance of an autonomous driving robot characterized by According to claim 9,
The repetition precision evaluation step may include accumulative summing of position errors measured for each number of times of travel when the number of times of travel of the robot satisfies a predetermined number; and
A method for evaluating the performance of an autonomous robot comprising the step of determining whether the cumulatively summed position error value exceeds a preset value. In the system for evaluating the performance of autonomous driving robots,
a map generation and storage unit for generating environment map information for performance evaluation of the robot and storing at least one map data;
a position setting unit that sets a starting point and a target point for performance evaluation of the robot;
a path planning evaluation unit that evaluates a time required for the robot to plan a path from the starting point to the target point;
a communication unit communicating with the robot and receiving data or transmitting a command from the robot;
a position measurement unit for measuring the position of the robot; and
An autonomous driving robot performance evaluation system comprising: an autonomous driving performance evaluation unit that evaluates the autonomous driving performance of the robot based on the position measured through the position measurement unit. According to claim 11,
The performance evaluation system of the autonomous driving robot, characterized in that it comprises: an obstacle generating unit for disposing at least one obstacle on the driving path of the robot, which is determined by the starting point and the target point. According to claim 11,
and a SLAM technology evaluation unit that evaluates a map generation speed based on the time required for the robot to generate a map when the SLAM technology is applied to the robot. According to claim 13,
The SLAM technology evaluation unit evaluates the map generation speed of the map and then evaluates the map data and matching rate of the generated map and the evaluation environment stored in the map generation and storage unit. Performance of the autonomous robot, characterized in that rating system. According to claim 11,
The self-driving robot performance evaluation system, characterized in that the self-driving performance evaluation unit evaluates the positional accuracy and repetition accuracy of the robot based on the positional difference between the robot and the target point.

Images